OpenRAG 0.2.2__tar.gz → 0.2.3__tar.gz

{openrag-0.2.2/src/openrag.egg-info → openrag-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openrag
-Version: 0.2.2
+Version: 0.2.3
 Summary: Add your description here
 Requires-Python: >=3.13
 Description-Content-Type: text/markdown

{openrag-0.2.2 → openrag-0.2.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "openrag"
-version = "0.2.2"
+version = "0.2.3"
 description = "Add your description here"
 readme = "README.md"
 requires-python = ">=3.13"

{openrag-0.2.2 → openrag-0.2.3}/src/api/settings.py

@@ -65,6 +65,16 @@ async def get_settings(request, session_manager):
             "ingest_flow_id": LANGFLOW_INGEST_FLOW_ID,
             "langflow_public_url": LANGFLOW_PUBLIC_URL,
             "edited": openrag_config.edited,
+            # Onboarding state
+            "onboarding": {
+                "current_step": openrag_config.onboarding.current_step,
+                "assistant_message": openrag_config.onboarding.assistant_message,
+                "selected_nudge": openrag_config.onboarding.selected_nudge,
+                "card_steps": openrag_config.onboarding.card_steps,
+                "upload_steps": openrag_config.onboarding.upload_steps,
+                "openrag_docs_filter_id": openrag_config.onboarding.openrag_docs_filter_id,
+                "user_doc_filter_id": openrag_config.onboarding.user_doc_filter_id,
+            },
             # OpenRAG configuration
             "providers": {
                 "openai": {
@@ -1087,6 +1097,10 @@ async def onboarding(request, flows_service, session_manager=None):
                         "Created OpenRAG Docs knowledge filter",
                         filter_id=openrag_docs_filter_id,
                     )
+                    # Save the filter ID to the config
+                    current_config.onboarding.openrag_docs_filter_id = openrag_docs_filter_id
+                    if not config_manager.save_config_file(current_config):
+                        logger.error("Failed to save openrag_docs_filter_id to config")
             except Exception as e:
                 logger.error(
                     "Failed to create OpenRAG Docs knowledge filter", error=str(e)
@@ -1353,6 +1367,65 @@ async def _update_langflow_chunk_settings(config, flows_service):
         raise
 
 
+async def update_onboarding_state(request):
+    """Update onboarding state in configuration"""
+    try:
+        await TelemetryClient.send_event(Category.ONBOARDING, MessageId.ORB_ONBOARD_START)
+        
+        # Parse request body
+        body = await request.json()
+        
+        # Validate allowed fields
+        allowed_fields = {
+            "current_step",
+            "assistant_message",
+            "selected_nudge",
+            "card_steps",
+            "upload_steps",
+            "openrag_docs_filter_id",
+            "user_doc_filter_id",
+        }
+        
+        # Check for invalid fields
+        invalid_fields = set(body.keys()) - allowed_fields
+        if invalid_fields:
+            return JSONResponse(
+                {
+                    "error": f"Invalid fields: {', '.join(invalid_fields)}. Allowed fields: {', '.join(allowed_fields)}"
+                },
+                status_code=400,
+            )
+        
+        # Update onboarding state using config manager
+        success = config_manager.update_onboarding_state(**body)
+        
+        if not success:
+            return JSONResponse(
+                {"error": "Failed to update onboarding state"},
+                status_code=500,
+            )
+        
+        logger.info(f"Onboarding state updated: {body}")
+        
+        return JSONResponse(
+            {
+                "message": "Onboarding state updated successfully",
+                "updated_fields": list(body.keys()),
+            }
+        )
+    
+    except json.JSONDecodeError:
+        return JSONResponse(
+            {"error": "Invalid JSON in request body"}, status_code=400
+        )
+    except Exception as e:
+        logger.error(f"Error updating onboarding state: {str(e)}")
+        return JSONResponse(
+            {"error": f"Failed to update onboarding state: {str(e)}"},
+            status_code=500,
+        )
+
+
 async def reapply_all_settings(session_manager = None):
     """
     Reapply all current configuration settings to Langflow flows and global variables.

{openrag-0.2.2 → openrag-0.2.3}/src/config/config_manager.py

@@ -4,7 +4,7 @@ import os
 import yaml
 from pathlib import Path
 from typing import Dict, Any, Optional
-from dataclasses import dataclass, asdict
+from dataclasses import dataclass, asdict, field
 from utils.logging_config import get_logger
 
 logger = get_logger(__name__)
@@ -85,6 +85,19 @@ class AgentConfig:
     system_prompt: str = "You are the OpenRAG Agent. You answer questions using retrieval, reasoning, and tool use.\nYou have access to several tools. Your job is to determine **which tool to use and when**.\n### Available Tools\n- OpenSearch Retrieval Tool:\n  Use this to search the indexed knowledge base. Use when the user asks about product details, internal concepts, processes, architecture, documentation, roadmaps, or anything that may be stored in the index.\n- Conversation History:\n  Use this to maintain continuity when the user is referring to previous turns. \n  Do not treat history as a factual source.\n- Conversation File Context:\n  Use this when the user asks about a document they uploaded or refers directly to its contents.\n- URL Ingestion Tool:\n  Use this **only** when the user explicitly asks you to read, summarize, or analyze the content of a URL.\n  Do not ingest URLs automatically.\n- Calculator / Expression Evaluation Tool:\n  Use this when the user asks to compare numbers, compute estimates, calculate totals, analyze pricing, or answer any question requiring mathematics or quantitative reasoning.\n  If the answer requires arithmetic, call the calculator tool rather than calculating internally.\n### Retrieval Decision Rules\nUse OpenSearch **whenever**:\n1. The question may be answered from internal or indexed data.\n2. The user references team names, product names, release plans, configurations, requirements, or official information.\n3. The user needs a factual, grounded answer.\nDo **not** use retrieval if:\n- The question is purely creative (e.g., storytelling, analogies) or personal preference.\n- The user simply wants text reformatted or rewritten from what is already present in the conversation.\nWhen uncertain → **Retrieve.** Retrieval is low risk and improves grounding.\n### URL Ingestion Rules\nOnly ingest URLs when the user explicitly says:\n- \"Read this link\"\n- \"Summarize this webpage\"\n- \"What does this site say?\"\n- \"Ingest this URL\"\nIf unclear → ask a clarifying question.\n### Calculator Usage Rules\nUse the calculator when:\n- Performing arithmetic\n- Estimating totals\n- Comparing values\n- Modeling cost, time, effort, scale, or projections\nDo not perform math internally. **Call the calculator tool instead.**\n### Answer Construction Rules\n1. When asked: \"What is OpenRAG\", answer the following:\n\"OpenRAG is an open-source package for building agentic RAG systems. It supports integration with a wide range of orchestration tools, vector databases, and LLM providers. OpenRAG connects and amplifies three popular, proven open-source projects into one powerful platform:\n**Langflow** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://www.langflow.org/)\n**OpenSearch** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://opensearch.org/)\n**Docling** – Langflow is a powerful tool to build and deploy AI agents and MCP servers [Read more](https://www.docling.ai/)\"\n2. Synthesize retrieved or ingested content in your own words.\n3. Support factual claims with citations in the format:\n   (Source: <document_name_or_id>)\n4. If no supporting evidence is found:\n   Say: \"No relevant supporting sources were found for that request.\"\n5. Never invent facts or hallucinate details.\n6. Be concise, direct, and confident. \n7. Do not reveal internal chain-of-thought."
 
 
+@dataclass
+class OnboardingState:
+    """Onboarding state configuration."""
+
+    current_step: int = 0
+    assistant_message: Optional[Dict[str, Any]] = field(default=None)
+    selected_nudge: Optional[str] = field(default=None)
+    card_steps: Optional[Dict[str, Any]] = field(default=None)
+    upload_steps: Optional[Dict[str, Any]] = field(default=None)
+    openrag_docs_filter_id: Optional[str] = field(default=None)
+    user_doc_filter_id: Optional[str] = field(default=None)
+
+
 @dataclass
 class OpenRAGConfig:
     """Complete OpenRAG configuration."""
@@ -92,6 +105,7 @@ class OpenRAGConfig:
     providers: ProvidersConfig
     knowledge: KnowledgeConfig
     agent: AgentConfig
+    onboarding: OnboardingState
     edited: bool = False  # Track if manually edited
 
     @classmethod
@@ -107,6 +121,7 @@ class OpenRAGConfig:
             ),
             knowledge=KnowledgeConfig(**data.get("knowledge", {})),
             agent=AgentConfig(**data.get("agent", {})),
+            onboarding=OnboardingState(**data.get("onboarding", {})),
             edited=data.get("edited", False),
         )
 
@@ -156,6 +171,7 @@ class ConfigManager:
             },
             "knowledge": {},
             "agent": {},
+            "onboarding": {},
         }
 
         # Load from config file if it exists
@@ -172,7 +188,7 @@ class ConfigManager:
                                 file_config["providers"][provider]
                             )
 
-                for section in ["knowledge", "agent"]:
+                for section in ["knowledge", "agent", "onboarding"]:
                     if section in file_config:
                         config_data[section].update(file_config[section])
 
@@ -294,6 +310,31 @@ class ConfigManager:
             logger.error(f"Failed to save configuration to {self.config_file}: {e}")
             return False
 
+    def update_onboarding_state(self, **kwargs) -> bool:
+        """Update onboarding state fields.
+
+        Args:
+            **kwargs: Onboarding state fields to update (current_step, assistant_message, etc.)
+
+        Returns:
+            True if updated successfully, False otherwise.
+        """
+        try:
+            config = self.get_config()
+            
+            # Update only the provided fields
+            for key, value in kwargs.items():
+                if hasattr(config.onboarding, key):
+                    setattr(config.onboarding, key, value)
+                else:
+                    logger.warning(f"Unknown onboarding field: {key}")
+            
+            # Save the updated config
+            return self.save_config_file(config)
+        except Exception as e:
+            logger.error(f"Failed to update onboarding state: {e}")
+            return False
+
 
 # Global config manager instance
 config_manager = ConfigManager()

{openrag-0.2.2 → openrag-0.2.3}/src/main.py

@@ -108,7 +108,7 @@ async def wait_for_opensearch():
 
     for attempt in range(max_retries):
         try:
-            await clients.opensearch.info()
+            await clients.opensearch.ping()
             logger.info("OpenSearch is ready")
             await TelemetryClient.send_event(Category.OPENSEARCH_SETUP, MessageId.ORB_OS_CONN_ESTABLISHED)
             return
@@ -384,7 +384,7 @@ async def ingest_default_documents_when_ready(services):
             await _ingest_default_documents_openrag(services, file_paths)
         else:
             await _ingest_default_documents_langflow(services, file_paths)
-        
+
         await TelemetryClient.send_event(Category.DOCUMENT_INGESTION, MessageId.ORB_DOC_DEFAULT_COMPLETE)
 
     except Exception as e:
@@ -457,6 +457,11 @@ async def _ingest_default_documents_langflow(services, file_paths):
         file_count=len(file_paths),
     )
 
+async def health_check(request):
+    """Simple liveness probe: Indicates that the OpenRAG Backend service is online and running."""
+    return JSONResponse({"status": "ok"}, status_code=200)
+
+
 async def opensearch_health_ready(request):
     """Readiness probe: verifies OpenSearch dependency is reachable."""
     try:
@@ -507,48 +512,48 @@ async def _ingest_default_documents_openrag(services, file_paths):
 
 async def _update_mcp_servers_with_provider_credentials(services):
     """Update MCP servers with provider credentials at startup.
-    
+
     This is especially important for no-auth mode where users don't go through
     the OAuth login flow that would normally set these credentials.
     """
     try:
         auth_service = services.get("auth_service")
         session_manager = services.get("session_manager")
-        
+
         if not auth_service or not auth_service.langflow_mcp_service:
             logger.debug("MCP service not available, skipping credential update")
             return
-        
+
         config = get_openrag_config()
-        
+
         # Build global vars with provider credentials using utility function
         from utils.langflow_headers import build_mcp_global_vars_from_config
-        
+
         global_vars = build_mcp_global_vars_from_config(config)
-        
+
         # In no-auth mode, add the anonymous JWT token and user details
         if is_no_auth_mode() and session_manager:
             from session_manager import AnonymousUser
-            
+
             # Create/get anonymous JWT for no-auth mode
             anonymous_jwt = session_manager.get_effective_jwt_token(None, None)
             if anonymous_jwt:
                 global_vars["JWT"] = anonymous_jwt
-            
+
             # Add anonymous user details
             anonymous_user = AnonymousUser()
             global_vars["OWNER"] = anonymous_user.user_id  # "anonymous"
             global_vars["OWNER_NAME"] = f'"{anonymous_user.name}"'  # "Anonymous User" (quoted for spaces)
             global_vars["OWNER_EMAIL"] = anonymous_user.email  # "anonymous@localhost"
-            
+
             logger.info("Added anonymous JWT and user details to MCP servers for no-auth mode")
-        
+
         if global_vars:
             result = await auth_service.langflow_mcp_service.update_mcp_servers_with_global_vars(global_vars)
             logger.info("Updated MCP servers with provider credentials at startup", **result)
         else:
             logger.debug("No provider credentials configured, skipping MCP server update")
-            
+
     except Exception as e:
         logger.warning("Failed to update MCP servers with provider credentials at startup", error=str(e))
         # Don't fail startup if MCP update fails
@@ -567,7 +572,7 @@ async def startup_tasks(services):
 
     # Configure alerting security
     await configure_alerting_security()
-    
+
     # Update MCP servers with provider credentials (especially important for no-auth mode)
     await _update_mcp_servers_with_provider_credentials(services)
 
@@ -578,7 +583,7 @@ async def startup_tasks(services):
             logger.info("Checking if Langflow flows were reset")
             flows_service = services["flows_service"]
             reset_flows = await flows_service.check_flows_reset()
-            
+
             if reset_flows:
                 logger.info(
                     f"Detected reset flows: {', '.join(reset_flows)}. Reapplying all settings."
@@ -676,7 +681,7 @@ async def initialize_services():
             await TelemetryClient.send_event(Category.CONNECTOR_OPERATIONS, MessageId.ORB_CONN_LOAD_FAILED)
     else:
         logger.info("[CONNECTORS] Skipping connection loading in no-auth mode")
-    
+
     await TelemetryClient.send_event(Category.SERVICE_INITIALIZATION, MessageId.ORB_SVC_INIT_SUCCESS)
 
     langflow_file_service = LangflowFileService()
@@ -1159,6 +1164,13 @@ async def create_app():
             ),
             methods=["POST"],
         ),
+        Route(
+            "/onboarding/state",
+            require_auth(services["session_manager"])(
+                settings.update_onboarding_state
+            ),
+            methods=["POST"],
+        ),
         # Provider health check endpoint
         Route(
             "/provider/health",
@@ -1167,6 +1179,12 @@ async def create_app():
             ),
             methods=["GET"],
         ),
+        # Health check endpoints
+        Route(
+            "/health",
+            health_check,
+            methods=["GET"],
+        ),
         Route(
             "/search/health",
             opensearch_health_ready,
@@ -1523,13 +1541,13 @@ async def create_app():
             while True:
                 try:
                     await asyncio.sleep(5 * 60)  # Wait 5 minutes
-                    
+
                     # Check if onboarding has been completed
                     config = get_openrag_config()
                     if not config.edited:
                         logger.debug("Onboarding not completed yet, skipping periodic backup")
                         continue
-                    
+
                     flows_service = services.get("flows_service")
                     if flows_service:
                         logger.info("Running periodic flow backup")

{openrag-0.2.2 → openrag-0.2.3/src/openrag.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openrag
-Version: 0.2.2
+Version: 0.2.3
 Summary: Add your description here
 Requires-Python: >=3.13
 Description-Content-Type: text/markdown